xzuyn

#2 opened 13 days ago by

choco9966

New activity in openbmb/Eurus-RM-7b 14 days ago

Fix example usage code

#4 opened 14 days ago by

xzuyn

New activity in alpindale/WizardLM-2-8x22B 19 days ago

Replace links with ones from Wayback Machine

#2 opened 19 days ago by

xzuyn

New activity in WhiteRabbitNeo/WRN-Chapter-1 22 days ago

`enhanced_instruction` contains the `response`

10

#2 opened 22 days ago by

xzuyn

New activity in mistralai/Mistral-7B-Instruct-v0.2 about 1 month ago

Was this model based of Mistral-7B-v0.2 from the start?

#72 opened about 1 month ago by

stduhpf

New activity in Open-Orca/SlimOrca-Dedup about 1 month ago

Grammar issues in system prompts.

#6 opened about 1 month ago by

xzuyn

New activity in hieunguyenminh/roleplay 3 months ago

Thanks for the set.

#2 opened 3 months ago by

xzuyn

New activity in PJMixers/limarp-perscengen-converted-combined 3 months ago

[bot] Conversion to Parquet

#1 opened 3 months ago by

parquet-converter

New activity in kashif/pickascore 4 months ago

What format is the jpg_0 & jpg_1?

3

#2 opened 4 months ago by

xzuyn

New activity in PocketDoc/Dans-TotSirocco-7b 6 months ago

love the model but it's a duplicate on the 7b leaderboard

#1 opened 6 months ago by

nisten

New activity in jbetker/tortoise-tts-v2 6 months ago

How does this compare to the finetuned-lj model?

#4 opened 6 months ago by

xzuyn

New activity in NoCrypt/blessed_vae 6 months ago

Can we get safetensors versions?

9

#1 opened 12 months ago by

xzuyn

New activity in Nebulous/lmsys-chat-1m-smortmodelsonly 7 months ago

How does `data_extra_filtered` differ from `data`?

#2 opened 7 months ago by

xzuyn

New activity in HuggingFaceH4/open_llm_leaderboard 7 months ago

Models with multiple submissions.

5

#322 opened 7 months ago by

xzuyn

New activity in mistralai/Mistral-7B-v0.1 7 months ago

Is `added_tokens.json` intended to be here?

#43 opened 7 months ago by

xzuyn

New activity in HWERI/openorca-multiplechoice-5k-comparisons 8 months ago

Dataset quality seems quite poor.

#1 opened 8 months ago by

xzuyn

New activity in beaugogh/openorca-multiplechoice-10k 8 months ago

Apologies. Incorrect repo.

#1 opened 8 months ago by

xzuyn

New activity in ICBU-NPU/FashionGPT-70B-V1.1 8 months ago

Merging Adapter.

#5 opened 8 months ago by

xzuyn

New activity in HuggingFaceH4/open_llm_leaderboard 8 months ago

`Running Evaluation Queue` seems to have gotten stuck on a model.

#268 opened 8 months ago by

xzuyn

WizardLM 30B model seems to rank way lower then it probably should be at.

#266 opened 8 months ago by

felixz

Please remove these models of mine from the leaderboard.

#250 opened 8 months ago by

xzuyn

Runtime error on CPU UPGRADE

#244 opened 8 months ago by

xzuyn

Can't submit QLoRA for eval because `Base model "meta-llama/Llama-2-7b-hf" was not found on hub!`

#241 opened 8 months ago by

xzuyn

Model failure.

#240 opened 8 months ago by

xzuyn

New activity in Xanthius/llama-token-counter 9 months ago

add box which shows encoded tokens, also add labels

#1 opened 9 months ago by

xzuyn

New activity in cognitivecomputations/open-instruct-uncensored 9 months ago

Can you upload a version which only uses the subset for Tulu?

#1 opened 9 months ago by

xzuyn

New activity in xzuyn/GPT-2-XL-1.5B-GGML 10 months ago

Could you please make this model?

#1 opened 10 months ago by

Hoioi

New activity in xzuyn/GPT2-RPGPT-8.48M 10 months ago

Adding `safetensors` variant of this model

#2 opened 10 months ago by

xzuyn

Adding `safetensors` variant of this model

#1 opened 10 months ago by

xzuyn

New activity in digitous/GPT4-x-MedOAlpacino-13B 11 months ago

Could we get original weights for this?

#4 opened 11 months ago by

xzuyn

New activity in xzuyn/GPT2-Stable-Diffusion-1.487M-Prompts-Deduped-6.86M 11 months ago

Adding `safetensors` variant of this model

#1 opened 11 months ago by

SFconvertbot

New activity in xzuyn/GPT-2-Stable-Diffusion-2.008M-Prompts-6.86M 11 months ago

Adding `safetensors` variant of this model

#1 opened 11 months ago by

SFconvertbot

New activity in openlm-research/open_llama_13b 11 months ago

Prompt format?

#3 opened 11 months ago by

iamrobotbear

New activity in xzuyn/MagicPrompt-Stable-Diffusion-124M-GGML 11 months ago

how should i use this model?

#1 opened 11 months ago by

dashuxu

New activity in timdettmers/guanaco-33b-merged 12 months ago

Prompt Format?

#4 opened 12 months ago by

xzuyn

New activity in TheBloke/guanaco-13B-GGML 12 months ago

Prompt Format.

3

#1 opened 12 months ago by

xzuyn

New activity in Aeala/VicUnlocked-alpaca-half-30b-LoRA 12 months ago

Question on alpaca format training.

#1 opened 12 months ago by

xzuyn

New activity in xzuyn/Alpacino-SuperCOT-13B 12 months ago

Is this model good?

#2 opened 12 months ago by

Yhyu13

New activity in xzuyn/StableLM-OpenAssistant-SFT-V7-Epoch-3-7B-GGML 12 months ago

file names

#1 opened 12 months ago by

wise-time

New activity in HuggingFaceH4/open_llm_leaderboard 12 months ago

Stuck on 4bit?

11

#17 opened 12 months ago by

xzuyn

New activity in digitous/13B-HyperMantis 12 months ago

Upload ggmlv2-model-q5_1.bin

#1 opened 12 months ago by

xzuyn

New activity in digitous/Alpacino30b 12 months ago

Make example memory a code block

#6 opened 12 months ago by

xzuyn

New activity in digitous/Alpacino13b 12 months ago

Make example memory a code block

#2 opened 12 months ago by

xzuyn

New activity in digitous/GPT4-x-MedOAlpacino-13B 12 months ago

Loving the model and your thought behind it <3, have you considered requantizing?

#1 opened 12 months ago by

khushman

New activity in xzuyn/Alpacino-SuperCOT-13B 12 months ago

Hello - I am tying to convert it to ggml but have error ....

#1 opened 12 months ago by

mirek190

New activity in khushman/medalpaca-13b-GGML-4bit 12 months ago

What'd you do to convert this?

#2 opened 12 months ago by

xzuyn

New activity in HuggingFaceH4/open_llm_leaderboard 12 months ago

Progress is too slow

#16 opened 12 months ago by

felixz

New activity in medalpaca/medalpaca-13b 12 months ago

KeyError: ('torch._tensor', '_rebuild_from_type_v2')

#3 opened 12 months ago by

xzuyn

New activity in reeducator/vicuna-13b-cocktail 12 months ago

Could we get the original weights?

#7 opened 12 months ago by

xzuyn

New activity in medalpaca/medalpaca-13b 12 months ago

change python code to use 13b instead of 7b

#2 opened 12 months ago by

xzuyn

New activity in reeducator/bluemoonrp-13b 12 months ago

Original weights?

#2 opened 12 months ago by

xzuyn

New activity in mosaicml/mpt-7b-storywriter 12 months ago

Apache license is irrevocable.

11

#5 opened 12 months ago by

xzuyn

New activity in reeducator/vicuna-13b-free about 1 year ago

You may want to add an "act-order" GPTQ quantization.

5

#22 opened about 1 year ago by

xzuyn

New activity in PygmalionAI/pygmalion-7b about 1 year ago

Reasoning behind bfloat instead of float?

14

#3 opened about 1 year ago by

xzuyn

New activity in medalpaca/medalpaca-7b about 1 year ago

ChatDoctor dataset question.